© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95536
    Prev
    Next
    INDEX
    Explanations

    references to unemployment rates and economic conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ìĥ
    -0.07
    eteria
    -0.06
     latch
    -0.06
     ones
    -0.06
    obil
    -0.06
    able
    -0.06
     é»Ħ
    -0.06
    ably
    -0.06
    spath
    -0.06
     Ukra
    -0.06
    POSITIVE LOGITS
    undler
    0.07
    hatt
    0.06
    @nate
    0.06
    oser
    0.06
    setDefault
    0.06
    /end
    0.06
    oses
    0.06
    anche
    0.06
    unce
    0.06
    antha
    0.06
    Activations Density 0.050%

    No Known Activations